多種機器學習方法在京津冀地區(qū)低能見度天氣預報中的應用

首頁 > 過刊瀏覽>2024年第44卷第2期 >362-374

多種機器學習方法在京津冀地區(qū)低能見度天氣預報中的應用
DOI:
                        
CSTR:
                        
作者:
                        
作者單位:
作者簡介:
通訊作者:
中圖分類號:P456
基金項目:天津市氣象局科研資助項目(202203ybxm02)

Application of multiple machine learning methods in low-visibility weather forecasting in Beijing-Tianjin-Hebei region

Author:

Affiliation:

Fund Project:

摘要

圖/表

訪問統(tǒng)計

參考文獻

相似文獻

引證文獻

資源附件

文章評論

摘要:

利用2017—2021年的ERA5再分析資料和京津冀國家站地面資料,結(jié)合多種機器學習方法建立預報模型,開展輕霧、大霧客觀預報。探討了再分析資料、地形因素的影響,并結(jié)合多模型集成、統(tǒng)計消空進一步優(yōu)化模型。結(jié)果表明:(1) XGBoost (eXtreme Gradient Boosting)、LightGBM (Light Gradient Boosting Machine)、隨機森林等集成學習方法的預報效果均優(yōu)于決策樹方法;(2)在引入ERA5再分析資料、地形建模后,XGBoost、LightGBM模型的預報性能顯著提高。相比僅使用地面要素建模,大霧預報的TS (Threat Score)提升了30%、32%,達到0.52、0.49,命中率分別為0.62、0.87。此外,經(jīng)過多模型集成后,輕霧、大霧預報的TS提升到了0.51、0.54;(3)2022年秋季一次大霧過程中,本方法提前72 h準確預報了京津冀地區(qū)的大霧,其中以LightGBM模型表現(xiàn)最好。0~72 h輕霧預報和0~36 h逐小時大霧預報的TS均達到0.3,預報準確率、時效性均優(yōu)于ECMWF (European Center for Medium Weather Forecasting)模式。

Abstract:

Based on observation data from the Beijing-Tianjin-Hebei National Weather Stations between 2017 and 2021, and ERA5 reanalysis data, a forecasting model for light fog and fog was developed by using a variety of machine learning algorithms. The study also investigated the influence of reanalysis and topographic factors on model performance, and utilized a method combining multi-model integration and statistical voiding to optimize the model. The main findings are as follows: (1)ensemble learning methods such as XGBoost (eXtreme Gradient Boosting), LightGBM (Light Gradient Boosting Machine), and random forest outperform the decision tree method in terms of low-visibility weather forecast ability; (2) the performance of the XGBoost and LightGBM models is significantly improved when introducing ERA5 reanalysis and topographic factors. Specifically, the TS (Threat Score) of fog forecast is 30% and 32% higher than that built on surface elements only, reaching 0.52 and 0.49, and the POD (Probability of Detection) is 0.62 and 0.87, respectively. In addition, the TS of light fog and fog forecast increase to 0.51 and 0.54 after stacking two models; (3) during a regional fog event in the fall of 2022, our methods accurately predict fog 72 h in advance. In particular, the LightGBM model performs best, with 0-36 h fog forecast TS and 0-72 h light fog forecast TS reaching 0.3, which is better than ECMWF (European Center for Medium Weather Forecasting) in accuracy and timeliness.

參考文獻

相似文獻

引證文獻

引用本文

張慶,張楠,陳子煊,陳宏.多種機器學習方法在京津冀地區(qū)低能見度天氣預報中的應用.氣象科學,2024,44(2):362-374 ZHANG Qing, ZHANG Nan, CHEN Zixuan, CHEN Hong. Application of multiple machine learning methods in low-visibility weather forecasting in Beijing-Tianjin-Hebei region. Journal of the Meteorological Sciences,2024,44(2):362-374

復制

文章指標

點擊次數(shù):
下載次數(shù):
HTML閱讀次數(shù):
引用次數(shù):

歷史

收稿日期:2023-03-24
最后修改日期:2024-01-31
錄用日期:
在線發(fā)布日期: 2024-05-17
出版日期:

文章二維碼

您是第位訪問者
氣象科學 ® 2026 版權(quán)所有
技術(shù)支持：北京勤云科技發(fā)展有限公司

抽查舔水白紧大视频,冲喜娘子超甜哒激情五月,亚洲黄色图片偷拍网站,亚洲三级黄片免费播放,91在线观看喷潮红桃,日韩精品在线观看一区二区,久久久久久久久久久久黄色片子,日产精品99久久久久久久久,欧洲亚洲另类图片小说

引用本文

分享

相關(guān)視頻

文章指標

歷史

文章二維碼

抽查舔水白紧大视频,冲喜娘子超甜哒 激情五月,亚洲黄色图片偷拍网站,亚洲三级黄片免费播放,91在线观看喷潮红桃,日韩精品在线观看一区二区,久久久久久久久久久久黄色片子,日产精品99久久久久久久久,欧洲亚洲另类图片小说

引用本文

分享

相關(guān)視頻

文章指標

歷史

文章二維碼

抽查舔水白紧大视频,冲喜娘子超甜哒激情五月,亚洲黄色图片偷拍网站,亚洲三级黄片免费播放,91在线观看喷潮红桃,日韩精品在线观看一区二区,久久久久久久久久久久黄色片子,日产精品99久久久久久久久,欧洲亚洲另类图片小说